> For the complete documentation index, see [llms.txt](https://docs.waveline.ai/extract/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.waveline.ai/extract/types/shape.md).

# Shape

We use Shape to specify what you want to extract from a document. It's an array where each element is a [DataShapeElement](/extract/types/datashapeelement.md).

```typescript
type Shape = DataShapeElement[];
```

## Create a Shape

There are three main ways to build a Shape for your use case:

* Use our intuitive [shape tools](https://waveline.ai/extract/dashboard/shape-tools) in the dashboard.
* Let us guess the shape you want to extract with our [guess-shape](/extract/endpoints/guess-shape.md) endpoint.
* Define your own shape based on our type definition.

## Examples

### Minimal Example

We extract the title of a provided newspaper article. The title should be a string.

```json
[
  {
    "name": "title",
    "type": "string",
    "description": "The title of this newspaper article",
    "isArray": false
  }
]
```

### Multiple fields

We extract multiple fields. Let's assume we process and invoice. We extract the name of the recipient and the total amount to pay.

```json
[
  {
    "name": "last_name",
    "type": "string",
    "description": "The last name of the recipient ",
    "isArray": false
  },
    "name": "total",
    "type": "number",
    "description": "Total amount to pay",
    "isArray": false
  }
]
```

### Array

If we have a field with multiple answers, we can set `isArray` to true. In this example, we process a conference paper and want to get back all the authors of that paper.

```json
[
  {
    "name": "authors",
    "type": "string",
    "description": "All authors that are part of this paper",
    "isArray": true
  }
]
```

### Object

In this example, we want to process mechanical parts that are mentioned in our document. For these parts, we specify an object with two properties: `part_id` and `shipping_price`. Both properties could be saved separately like in the example [above](#multiple-fields), but in this case, we can simply save them as properties of this object:

```json
[
  {
    "name": "part",
    "type": "object",
    "description": "A mechanical part to be shipped.",
    "isArray": false,
    "elements": [
      {
        "name": "part_id",
        "type": "number",
        "description": "The id of that part",
        "isArray": false
      },
      {
        "name": "shipping_price",
        "type": "string",
        "description": "Shipping price of that part",
        "isArray": false
      }
    ]
  }
]
```

### Advanced Shape

This example is a more complex variation of the [previous one](#object). Since our document can contain multiple parts to ship, we can simply set the `isArray` property to `true` and our results will contain a list of parts! Additionally, we can create another field called date that holds the current date. 

```json
"shape": [
  {
    "name": "part",
    "type": "object",
    "description": "Mechanical parts to be shipped",
    "isArray": true,
    "elements": [
      {
        "name": "part_id",
        "type": "number",
        "description": "The id of that part",
        "isArray": false
      },
      {
        "name": "sizes",
        "type": "string",
        "description": "Different sizes that this part can be produced",
        "isArray": true
      }
    ]
  },
  {
    "name": "date",
    "type": "string",
    "description": "Current date in the format MM-DD-YYYY",
    "isArray": false
  }
]
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.waveline.ai/extract/types/shape.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.